Automated landmark extraction from three-dimensional whole body scanned data

Abstract

A method for automated landmark extraction from three-dimensional whole body scanned data extracts feature points as landmarks from a plurality of point clouds obtained from a three-dimensional whole body scanner, without pre-making the landmarks on a human body before scanning. The system includes: (1) Silhouette analysis, which projects three-dimensional body scanned data onto a two-dimensional surface and observes the variations in curvature and depth; (2) Minimum circumference, which uses the variations of the circumference of body parts to define the locations of the landmarks and feature lines; (3) Gray-scale detection, which converts the color information of human body from RGB values into gray-scale values to locate the landmarks with greater variations in brightness; and (4) Human-body contour plot, which simulates the sense of touch to locate landmarks by finding the prominent and concave parts on the human body.

Description

RELATED U.S. APPLICATIONS [0001] Not applicable. STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT [0002] Not applicable. REFERENCE TO MICROFICHE APPENDIX [0003] Not applicable. FIELD OF THE INVENTION [0004] This invention involves a method for extracting landmarks from three-dimensional whole body scanned data automatically. It is an invention to extract feature points as landmarks from a plurality of point clouds obtained from a three-dimensional whole body scanner, without pre-making the landmarks on a human body before scanning. Based on the principles of simulating human vision and sense of touch, several algorithms for different kinds of landmarks were developed depending on each geometric characteristic. The algorithms include silhouette analysis, minimum circumference, gray-scale detection, and human-body contour plots. BACKGROUND OF THE INVENTION [0005] Since three-dimensional whole body scanners were first introduced in the 1990's, many countries have investe...

AI Technical Summary

Benefits of technology

[0013] With measurements calculated from whole body scanned data using this invention, it is easier to make customized clothes that requires higher fitness, such as business suits, Mandarin dress, swimsuits, and undergarments. When integrated with e-commerce and Internet technologies, it has the

Problems solved by technology

However, even though this method yields higher identification rates, it is not time-efficient, especially when used in large projects or surveys.

In these cases, the progress of data analysis often lags far behind that of scanning.

Therefore, it requires considerable efforts after scanning.

Although these methods had indeed shorten the time for identifying color markers, it was still unable to shorten the time for manual pre-marking and to avoid human errors that is derived from this task.

However, individual variations in body shapes inevitably reduce the identification rate of these methods, especially when they are applied to a subject of the race that is not originally designed for.

Therefore, there are still difficulties in extracting landmarks successfully and accurately.

Hence, to develop a practical method for landmark extraction is an important issue that the industry concerned.

Images